© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 139389
    Prev
    Next
    INDEX
    Explanations

    Pinocchio and lies

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_16_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ですが
    0.69
    防
    0.64
    зации
    0.63
    និង
    0.63
    이지만
    0.62
    때
    0.61
    ياء
    0.61
    과
    0.59
    でも
    0.59
    zył
    0.57
    POSITIVE LOGITS
    in
    0.73
    ar
    0.70
     c
    0.66
     Domino
    0.64
    c
    0.62
     one
    0.60
     b
    0.59
     an
    0.58
     car
    0.58
    si
    0.58
    Activations Density 0.000%

    No Known Activations